CHAPTER 8

CONFIDENCE INTERVALS
PART A
WHEN THE
POPULATION STANDARD
DEVIATION
IS KNOWN
 How to find the confidence interval for the
population mean when σ is known.

WHAT WILL I LEARN IN

CHAPTER 8 PART A?
MAKING ESTIMATIONS BASED ON SAMPLES
Inferential statistics: the branch of statistics that consists of
generalizing about a population based on a sample.
• Statistical measures used to estimate a
population statistic are called estimators.
Types of Estimators
Point Interval Estimates
Estimates
Definition: A specific numerical Definition: A range of values
value estimate of a parameter. used to estimate a parameter.

Example: If we took a sample Example: If we took a sample

of 30 HU freshman and found of 30 HU freshman and found
the mean age to be 21 and the the mean age to be 21 and the
standard deviation to be 2.75, standard deviation to be 2.75,
we could infer that the mean we could say with 95%
age of all freshman at HU is 21 confidence that the mean age
and that the standard deviation of all freshman at HU is
of all freshman at HU is 2.75. between 20 and 22 years, or
with 99% confidence that the
mean age of all freshman at
Clearly from our example of an interval estimate there are 2
distinct parts:
“we could say with 95% confidence
that the true mean of the ages of all
freshman at HU is
between 20 and 22 years”
The example above is called a confidence interval. The two main
components are:
Confidence Level: Confidence Interval:
The probability that the The interval estimate
interval estimate will obtained by using the
contain the parameter. sample mean and
(Most often, 90%, 95%, or adding/subtracting a
99% confidence levels are margin of error. (The
used). margin of error is a
calculation that involves
the confidence level).
Important note:
 Often times, certain assumptions must be met before using inferential
statistic techniques. Some common assumptions may be:
• Samples were randomly selected
• The sample size is greater than or equal to 30
• The sample is normally distributed
Formula for the Confidence Interval of the Mean for
when (population standard deviation) is known
…the sample
mean plus and
minus…

𝑋 − 𝑧 𝛼 /2
( 𝜎
√𝑛 )
<𝜇< 𝑋 + 𝑧 𝛼 /2
( 𝜎
√𝑛 )
The
population
mean is
between…
the “margin
of error”
AKA
“maximum
error of the
estimate”
 𝑋 − 𝑧 𝛼 /2
The margin of error: ( )
𝜎
√𝑛
<𝜇< 𝑋 + 𝑧 𝛼 /2
( )
𝜎
√𝑛
“E” the
margin of
error

The margin of error has two components: a critical value (z-

score) and standard deviation. Remember that a z-score simply
represents how many standard deviations a value is away from
the mean. If we multiply a z-score times the standard
deviation, we get the distance a particular value is from the

( )
mean.
𝜎
𝑧
Z-score 𝛼/ 2 √𝑛 Standard
or Deviation
Critical (accounting for
Value sample size)
 Critical
𝑋 − 𝑧 𝛼 /2
values : ( )
𝜎
√𝑛
<𝜇< 𝑋 + 𝑧 𝛼 /2
( )
𝜎
√𝑛
Example of what the critical values represent in a 95%
confidence interval
represents the non-
shaded area in the
tails.

For a 90% confidence interval,

critical
For a 95% confidence interval, values for
typical
For a 99% confidence interval, confidence
levels
Rounding Rules for a
Confidence Interval for a Mean
When you are computing a confidence interval for a population mean by
using raw data, round the confidence level limits to one more decimal place
than there was in the original raw data.

When you are given only the summary statistics, round the confidence
interval limits to the same number of decimal places used for the sample
statistics.

Remember, these rules are not set in stone. Round using common sense.
For example, if the data variable is in dollars, it would make sense to round
to two decimal places. If the lower bound of the interval is a negative
number, but the variable is weight of underweight babies born, then using
a zero for the lower bound would make more sense.

Round any intermediate computations to 4 decimal places (again,

this is for consistency of homework results, not part of a statistics
dogma).
Example: Days It Takes to Sell a Geo Metro
A researcher wishes to estimate the number of days
it takes an automobile dealer to sell a Chevrolet Geo
Metro. A random sample of 50 cars had a mean time
on the dealer's lot of 54 days. Assume the population
standard deviation to be 6 days. Find the 95%
confidence interval of the population mean.
Using GeoGebra Step 2: Input
Step 1: From the probability the
calculator, click the statistics confidence
tab and choose Z-Estimate of level,
a mean. sample
mean,
sample
standard
deviation
and sample
size.
Step 3: Press
enter and
scroll down
to your
results.
 52 < µ < 56

1.6631 is the Margin of Error

Example: Days It Takes to Sell a Geo
A researcher wishes to estimate the number of days it
takes an automobile dealer to sell a Chevrolet Geo. A
random sample of 50 cars had a mean time on the
dealer's lot of 54 days. Assume the population standard
deviation to be 6 days. Find the 95% confidence interval of
the population mean.
What I expect to see in your written
Step 1: Capture a
work:
screenshot of your 𝐸 ≈ 1 .6631
GeoGebra work.
Explicitly identify and write
the margin of error (to 4
decimal places).
Step 2: Follow the
confidence interval 54 − 1.6631< 𝜇<54 +1.6631
formula to write in the
values of the mean and 52.3369<𝜇 <55.6631
margin of error (in
inequality notation) and 52 <𝜇 <56
simplify. Round your final
interval according to the
rounding rule(s) that apply. We can say, with 95% confidence, that the
Step 3: make
the true mean number of days it takes to sell an
confidence Geo is between 52 and 56 days.
statement
 Example: Waiting in the Emergency Room
A survey of 30 randomly selected emergency room patients found
that the average waiting time for treatment was 174.3 minutes.
Assuming that the population standard deviation is 46.5 minutes find
the 99% confidence interval of the population mean.

Step 1: Capture a screenshot of

your GeoGebra work.
Explicitly identify and write the
margin of error (4 decimal
places).

Step 2: Follow the confidence

interval formula to write in the
values of the mean and
margin of error (in inequality
notation) and simplify. Round
your final interval according to
the rounding rule(s) that apply.

Step 3: make
the confidence
statement
Example: Waiting in the Emergency Room
A survey of 30 randomly selected emergency room
patients found that the average waiting time for
treatment was 174.3 minutes. Assuming that the
population standard deviation is 46.5 minutes find
the 99% confidence interval of the population mean.
Step 1: Capture a
screenshot of your 𝐸≈ 2 1.868
GeoGebra work.
Explicitly identify and write
the margin of error (4
Step 2: Follow
decimal the
places).
confidence interval formula
to write in the values of 174.3 −21.868 <𝜇< 174.3+21.868
the mean and margin of
error (in inequality 152.432 <𝜇 <196.168
notation) and simplify.
Round your final interval 152.4 <𝜇<196.2
according to the rounding
rule(s)
Step 3:that apply. We can say, with 99% confidence, that the true
make
the mean number of minutes it takes to receive
confidence treatment in the emergency room is between 152.4
statement and 196.2 minutes.
 You try it! Commuting Time for HU Students:
A survey of 200 HU undergraduate students found that the sample
mean commute time (per week) to campus was 2.5 hours.
Assuming the population standard deviation was 0.5 hour, find the
95% confidence interval of the population mean.

Step 1: Capture a screenshot of

your GeoGebra work.
Explicitly identify and write the
margin of error (4 decimal
places).

Step 2: Follow the confidence

interval formula to write in the
values of the mean and
margin of error (in inequality
notation) and simplify. Round
your final interval according to
the rounding rule(s) that apply.

Step 3: make the

confidence
statement
 ESTIMATION AS A
TYPE OF INFERENCE
Click icon to add picture

cedure
i n g pro
pl
Sam

Population of all HU
Sample HU undergraduate
undergraduate
students students
N = 200 N = 795

t
bou
a
n ce
er e
i n f
a n t i o n t i on
a ke pula pula ion
M
e po po viat
Calculation of th en a de
d
Sample Mean Giv ndar
sta
“ LET’S EXPLORE THE VISUAL ON PAGE
250 OF YOUR TEXTBOOK REGARDING
SAMPLE SIZE

”
The Relationship between
sample size and
confidence interval width.
 ( ) 𝜎
USING THE MARGIN OF ERROR TO
DETERMINE HOW BIG A SAMPLE 𝐸 =𝑧 𝛼/ 2
SIZE N SHOULD BE √𝑛
A scientist wishes to estimate the average depth of a river. He
wants to be 99% confident that the estimate is accurate within 2
feet. From a previous study, the standard deviation of the depths
measured was 4.33 feet.
Formula for the minimum sample size needed
for an interval estimate of the population
mean.
( )
𝟐
𝒛 𝜶 /𝟐 ∙ 𝝈
𝒏=
𝑬

( )
2
2.58 ∙ 4.33
𝑛=
2
𝑛=31.2 When determining sample size, round
up.
To be 99% confident that the estimate is within 2 feet of the true
mean depth, the scientist needs a minimum of 32 measurement
samples.